Patrik Viktor

Autonomous vehicles depend on heterogeneous sensing systems whose performance varies with range, illumination, weather, object material, traffic geometry, contamination, calibration quality, and cyber-physical interference. This PRISMA 2020 and PRISMA-S systematic review synthesized 65 peer-reviewed primary studies selected from 2143 records identified through four databases. After removal of 793 records before screening, 1350 titles and abstracts were screened; 273 full texts were assessed and 208 were excluded with documented reasons. The final evidence base covers cameras, LiDAR, radar, thermal and event cameras, GNSS/IMU localization, calibration, synchronization, multimodal fusion, adverse-weather perception, sensor-health monitoring, and fault-tolerant perception. No modality was universally superior: comparative performance depended on hardware generation, dataset, environmental severity, range, and metric. Direct evidence was strongest for component-level perception and controlled degradation, whereas health-conditioned fusion, ODD restriction, and minimum-risk behavior were supported mainly by partial experimental evidence and safety-oriented synthesis. The review therefore proposes, rather than claims to validate, a reliability-aware architecture that separates sensor health from task confidence, preserves uncertainty and provenance, adapts fusion, and constrains operation when residual evidence is insufficient. The review was retrospectively registered in PROSPERO on 30 July 2026 (CRD420261465869).

Autonomous vehicles increasingly require capabilities that extend beyond perception towards contextual understanding, semantic reasoning, and explainable decision-making. Knowledge graphs (KGs) have emerged as a promising solution by integrating heterogeneous sensor data, traffic regulations, domain knowledge, and contextual information into unified semantic frameworks. This review systematically examines knowledge graph-based intelligent reasoning in autonomous driving through a PRISMA 2020-guided analysis of 47 peer-reviewed studies identified from the literature published from 1 January 2018 to 31 January 2026. The findings reveal that semantic scene understanding and ontology-based representations currently dominate the field, with 66.0% of studies integrating knowledge graphs with deep learning approaches. Neuro-symbolic methods and explainable AI components were identified in 38.3% and 34.0% of publications, respectively, indicating increasing research interest in hybrid and transparent AI architectures. The analysis further demonstrates that 80.9% of studies remain limited to benchmark datasets and simulation environments, whereas only 19.1% provide real-world validation, suggesting relatively low technological maturity and limited industrial readiness. Although KG-enabled approaches substantially improve contextual awareness, hidden hazard anticipation, and explainability compared with conventional perception-centric architectures, major challenges remain regarding scalability, ontology interoperability, semantic error propagation, real-time reasoning, and certification requirements. The review identifies the convergence of knowledge graphs, large language models, and neuro-symbolic AI as a promising direction for next-generation autonomous driving systems. Future research should therefore focus on uncertainty-aware reasoning, adaptive explainability, standardised evaluation methodologies, and certification-oriented real-world deployment strategies.

The rapid progress of sensing technologies, artificial intelligence, and embedded computing has significantly accelerated the development of autonomous vehicles. Among the core challenges of higher-level driving automation, reliable environmental perception remains one of the most critical. This review presents a systematic PRISMA-based analysis of multimodal sensor technologies and fusion architectures applied in autonomous driving, based on 66 peer-reviewed studies published between 2014 and 2025. The study examines the operational characteristics, advantages, and limitations of major sensing modalities, including cameras, LiDAR, radar, ultrasonic sensors, and GNSS/IMU-based localization systems. Particular attention is given to multimodal fusion strategies, covering early, mid-level, high-level, and transformer-based architectures that combine complementary sensor information to improve perception robustness and decision reliability. The review further synthesizes current evidence on performance under adverse environmental conditions, benchmark validation practices, real-time computational constraints, and the growing role of functional safety frameworks such as ISO 26262 and SOTIF. Emerging research directions, including 4D radar, self-supervised long-range fusion, foundation models, and cooperative V2X perception, are also discussed. The findings indicate that multimodal sensor fusion is a highly effective architectural strategy for improving scalability, fail-operational robustness, and certifiable safety in autonomous driving systems, particularly in higher-level automation scenarios. Future research should focus on uncertainty-aware fusion, explainable cross-modal reasoning, large-scale real-world validation, and efficient hardware–software co-design to support robust Level 4–5 vehicle autonomy.

Autonomous driving systems require the integration of heterogeneous sensor data, distributed V2X communication, and safety-critical decision-making into coherent and interpretable world models. This review provides a systematic analysis of knowledge graph (KG)-based approaches in autonomous driving between 2015 and 2025, following a PRISMA-aligned methodology. The literature is organised along a perception → representation → reasoning → decision taxonomy, covering traffic ontologies, V2X knowledge integration, dynamic KG updates, real-time reasoning architectures, and benchmark datasets. A clear shift from static representational ontologies toward predictive and, in a smaller subset, closed-loop validated neuro-symbolic architectures. Knowledge graphs emerge as semantic integration layers that improve contextual reasoning, explainability, and rule compliance in safety-critical environments. Key challenges include scalable real-time reasoning, standardised evaluation frameworks, and safety-aligned integration of learning-based components.

Autonomous vehicles rely on complex sensing systems to perceive their environment and ensure safe operation. This review analyses the main sensor technologies used in self-driving vehicles, including cameras, LiDAR, radar, ultrasonic sensors and GNSS/IMU-based localisation systems. A core set of 40 primary research articles was systematically analysed to compare the capabilities, limitations and integration challenges of sensing technologies used in autonomous vehicles. In addition to these primary studies, further references were included to provide background information and describe emerging developments in autonomous sensing systems. The review shows that no single sensor technology can provide reliable perception under all environmental conditions. Camera systems offer rich visual information but are sensitive to lighting and weather conditions, while LiDAR provides highly accurate three-dimensional geometry but suffers from signal attenuation in rain and fog. Radar sensors demonstrate superior robustness in adverse weather and enable direct velocity measurement, although their spatial resolution remains limited compared to optical sensors. As a result, modern autonomous vehicles rely on multi-sensor fusion architectures that combine complementary sensing modalities to improve reliability and safety. The analysis also identifies several key research gaps in the current literature. In particular, there is a lack of systematic evaluation of trade-offs between sensor performance, computational requirements and vehicle energy consumption. Furthermore, the safety certification of artificial intelligence-based perception systems and the integration of emerging technologies such as FMCW LiDAR and terahertz radar remain open research challenges. Overall, the results suggest that the future of autonomous vehicle perception will depend not only on improvements in individual sensors but also on robust sensor fusion architectures, safety-certified AI models and energy-efficient sensor processing platforms. These findings provide guidance for researchers and engineers developing next-generation sensing systems for autonomous driving.

The successful integration of autonomous vehicle (AV) technologies into future mobility systems depends not only on technological maturity but also on user acceptance and perceived value. While existing research has identified several demographic determinants of AV acceptance, the role of educational background—particularly differences between humanities and STEM graduates—has received limited attention within the context of user-centred mobility research. This study examines how educational background and gender influence attitudes toward autonomous vehicle technologies using a large-scale survey conducted in Hungary (N = 8663). The analysis combines non-parametric statistical tests with effect size measures, exploratory factor analysis, and structural equation modelling (SEM) to capture both group differences and underlying attitudinal mechanisms. The results indicate no meaningful differences between humanities and STEM graduates in overall acceptance of autonomous vehicles or trust in the technology. Statistically significant differences are observed only in two dimensions: willingness to spend on autonomous driving features and expectations regarding improved travel speed. However, effect size analyses reveal that these differences are negligible in practical terms, indicating substantial overlap in user attitudes. SEM results show that educational background does not directly determine acceptance of autonomous vehicle technologies. Instead, its influence is mediated through three latent attitude dimensions relevant for electric and autonomous mobility adoption: willingness to invest, functional expectations (e.g., time savings and convenience), and safety orientation. Humanities graduates—especially men—exhibit slightly higher financial openness toward autonomous features, whereas STEM graduates place greater emphasis on functional performance. Safety-related attitudes play a central mediating role, with gender-specific patterns. By integrating large-sample effect size interpretation with SEM-based modelling, this study provides a nuanced understanding of user acceptance of autonomous vehicle technologies. The findings suggest that differences between educational groups reflect variations in attitudinal emphasis rather than fundamental divides, offering relevant insights for user-centred AV development, mobility policy design, and communication strategies in the transition toward automated and electric mobility systems.

The rapid development of autonomous vehicle technologies represents a major transformation in contemporary transportation systems; however, their successful integration depends not only on technological maturity but also on societal acceptance. This study investigates public attitudes toward autonomous vehicles, with particular emphasis on generational and gender-based differences, aiming to identify key factors influencing acceptance, usage intention, and purchase-related decision-making. A quantitative, cross-sectional research design was applied using an online questionnaire survey conducted between January and September 2025. The final sample consisted of 655 respondents, with a balanced gender distribution and representation across multiple generational cohorts. Statistical analyses included one-way and two-way analysis of variance (ANOVA), complemented by non-parametric tests when distributional assumptions were not fully met. The results indicate significant generational differences across all examined dimensions. Younger generations, particularly Generations Y and Z, exhibit significantly higher willingness to try autonomous vehicles, greater openness to new technologies, and stronger consideration of autonomous functions in vehicle purchasing decisions. Gender-based differences were also identified, with men generally demonstrating higher technological openness than women. Moreover, a significant interaction effect between generation and gender was found, suggesting that gender differences vary across generational groups and are less pronounced among younger cohorts. Despite these contributions, the study has several limitations. Its cross-sectional design captures attitudes at a single point in time and does not allow causal inference or longitudinal analysis of attitude change. The use of self-reported, hypothetical measures may not fully reflect actual behaviour in real-world adoption scenarios. Additionally, online data collection may introduce self-selection bias, favouring respondents with higher digital literacy and technological interest. Overall, the findings highlight the importance of considering demographic heterogeneity when developing, communicating, and regulating autonomous vehicle technologies, while also underscoring the need for longitudinal and behaviour-based research in future studies.

Decisions made by pilots and drivers suffering from depression can endanger the lives of hundreds of people, as demonstrated by the tragedies of Germanwings flight 9525 and Air India flight 171. Since the detection of depression is currently based largely on subjective self-reporting, there is an urgent need for fast, objective, and reliable detection methods. In our study, we present an artificial intelligence-based system that combines iris-based identification with the analysis of pupillometric and eye movement biomarkers, enabling the real-time detection of physiological signs of depression before driving or flying. The two-module model was evaluated based on data from 242 participants: the iris identification module operated with an Equal Error Rate of less than 0.5%, while the depression-detecting CNN-LSTM network achieved 89% accuracy and an AUC value of 0.94. Compared to the neutral state, depressed individuals responded to negative news with significantly greater pupil dilation (+27.9% vs. +18.4%), while showing a reduced or minimal response to positive stimuli (−1.3% vs. +6.2%). This was complemented by slower saccadic movement and longer fixation time, which is consistent with the cognitive distortions characteristic of depression. Our results indicate that pupillometric deviations relative to individual baselines can be reliably detected and used with high accuracy for depression screening. The presented system offers a preventive safety solution that could reduce the number of accidents caused by human error related to depression in road and air traffic in the future.

A közúti közlekedés biztonsága kiemelkedő társadalmi jelentőséggel bír, különösen az autonóm járműtechnológia térnyerésének korában. Tanulmányunk célja az önvezető és a hagyományos járművek féktávolságának összehasonlító elemzése, különböző útviszonyok és sebességtartományok figyelembevételével. A vizsgálat középpontjában a reakcióidő áll, mely döntő befolyással bír a megállási távolságra. Az eredmények azt mutatják, hogy az önvezető rendszerek – 0,15 másodperces átlagos reakcióidejükkel – minden vizsgált körülmény között rövidebb féktávolságot produkálnak, mint az emberi vezetők, akiknél ez az érték 0,8–2 másodperc között változhat, különösen zavaró tényezők (pl. mobiltelefon-használat) hatására. A kutatás kimutatta, hogy városi környezetben az önvezető járművek akár 4,86 méterrel, míg autópályán 23 méterrel korábban képesek megállni, ami kritikus különbséget jelenthet baleseti szituációk-ban. A tanulmány megerősíti az autonóm rendszerek biztonsági előnyeit, és alátámasztja azt a hipotézist, hogy az önvezető technológia mérhetően képes csökkenteni a közúti balesetek számát.

The rapid technological advancement of autonomous vehicles (AVs)—as exemplified by recent research such as Enhancing High-Speed Cruising Performance of Autonomous Vehicles Through Integrated Deep Reinforcement Learning Framework (IEEE Transactions on Intelligent Transportation Systems, 2025)—raises pressing societal questions about their acceptance. Although numerous studies have examined attitudes toward autonomous vehicles in recent years, most research is limited to a single country, age group, or small sample. As a result, there is still a lack of empirical analyses comparing multiple generations and conducted on large samples that would provide a comprehensive picture of the age-determining factors of social acceptance of AVs. The present study aims to fill this gap with a questionnaire survey of 8663 people, which examines the trust, technology acceptance, and willingness to use autonomous vehicles among the Baby Boomer, X, Y, Z, and Alpha generations using Likert scale items. We used the Kruskal–Wallis test to explore the differences between generations. Our results show significant differences: while Generations Z and Alpha show remarkable openness and trust in AV technology, the Baby Boomer generation shows marked skepticism. The novelty of the research is that it provides large-scale, multi-generational comparative data, thus shedding light from a new perspective on the cultural, experiential, and trust patterns that determine the social acceptance of autonomous vehicles, beyond technological factors. The limitations of the study include self-reported data collection, geographical limitations (Hungary), and the lack of actual driving experience among the Alpha generation, which may affect the validity of the responses. However, these factors point the way for future international and qualitative research. The results can provide practical guidance for decision-makers, developers, and urban planners in developing inclusive, generation-sensitive transportation policies and communication strategies.